Measuring Fine-Grained Negotiation Tactics of Humans and LLMs in Diplomacy

ACL ARR 2025 July Submission1017 Authors

Abstract: The study of negotiation styles dates back to Aristotle's ethos-pathos-logos rhetoric. While prior efforts study the success of negotiation agents, we shift the focus towards the styles of persuasive strategies. Our focus is the strategic dialogue board game Diplomacy, which affords rich natural language negotiation and measures of game success. We used LLM-as-a-judge to annotate a large human-human set of Diplomacy games for fine-grained negotiation tactics from a sociologically-grounded taxonomy. Using a combination of the It Takes Two and WebDiplomacy dataset, we show that there are strong correlations between the negotiation features and success in the context of the Diplomacy game. Lastly, we craft LLM negotiation agents and show that we can make the negotiation tactics of the LLM agents' more human-like through fine-tuning.

Paper Type: Long

Research Area: Human-Centered NLP

Research Area Keywords: human-centered evaluation

Contribution Types: Model analysis & interpretability

Languages Studied: English

Reassignment Request Area Chair: This is not a resubmission

Reassignment Request Reviewers: This is not a resubmission

A1 Limitations Section: This paper has a limitations section.

A2 Potential Risks: Yes

A2 Elaboration: Section 8

B Use Or Create Scientific Artifacts: Yes

B1 Cite Creators Of Artifacts: Yes

B1 Elaboration: Section1, 2, 3, 4, 5, 6

B2 Discuss The License For Artifacts: N/A

B3 Artifact Use Consistent With Intended Use: Yes

B3 Elaboration: Section 1, 3, 4, 6

B4 Data Contains Personally Identifying Info Or Offensive Content: N/A

B5 Documentation Of Artifacts: Yes

B5 Elaboration: Appendix

B6 Statistics For Data: Yes

B6 Elaboration: Section 4, 7, Appendix

C Computational Experiments: Yes

C1 Model Size And Budget: Yes

C1 Elaboration: Section 4, 6, Appendix

C2 Experimental Setup And Hyperparameters: Yes

C2 Elaboration: Appendix

C3 Descriptive Statistics: Yes

C3 Elaboration: Section 4, 5, 6

C4 Parameters For Packages: Yes

C4 Elaboration: Appendix

D Human Subjects Including Annotators: Yes

D1 Instructions Given To Participants: Yes

D1 Elaboration: Appendix

D2 Recruitment And Payment: N/A

D3 Data Consent: N/A

D4 Ethics Review Board Approval: N/A

D5 Characteristics Of Annotators: N/A

E Ai Assistants In Research Or Writing: No

E1 Information About Use Of Ai Assistants: N/A

Author Submission Checklist: yes

Submission Number: 1017